© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148090
    Prev
    Next
    INDEX
    Explanations

    loading .mat files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    市政
    0.48
     reinforce
    0.46
     `/
    0.44
    ဒ
    0.44
     شكله
    0.43
     sharpen
    0.42
     এলিট
    0.42
     interact
    0.42
     achieve
    0.41
     accomplish
    0.41
    POSITIVE LOGITS
    IAS
    0.48
    iale
    0.44
     っ
    0.44
    ."
    0.42
     McKe
    0.42
    สัมพันธ์
    0.42
    iosis
    0.41
     स्टे
    0.41
    ราคา
    0.41
    BleStatus
    0.41
    Activations Density 0.000%

    No Known Activations